Automatic Convolutional Neural Architecture Search for Image Classification Under Different Scenes

Yu, Weiren; Zhou, Tianbao; Liu, Lei; Xia, Chunlei

doi:10.1109/access.2019.2906369

Cited by 43 publications

(20 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Binary CSA has shown better performance in terms of test error as compared to previous methods. However, CNAS [50] has achieved similar performance with less number of parameters. Binary CSA can achieve better results in the terms of a smaller number of parameters as well if applied to a more efficient search space.…”

Section: Resultsmentioning

confidence: 91%

Image Classification Based on Automatic Neural Architecture Search Using Binary Crow Search Algorithm

et al. 2020

View full text Add to dashboard Cite

Neural architectures have accelerated the advancement in various domains by enabling automatic pattern detection, image classification, audio recognition, and face recognition etc. However, they are computationally expensive to design and expert knowledge in various domains is required. In this paper, a swarm intelligence algorithm is proposed to search for novel architectures without human intervention that can achieve comparable performance to those of human-designed architectures. This work is inspired by current neural architecture search approaches based on reinforcement learning and genetic algorithm. However, not much attention is paid towards swarm intelligence metaheuristics-based neural architecture search. A framework is proposed for automatically designing neural architectures based on a swarm intelligence metaheuristic: Crow Search Algorithm. First, Crow Search Algorithm is integrated with binary network representation. To make it compatible for Neural Architecture Search, the original distance metric is replaced with hamming distance-based similarity measure. Second, the tuning parameters of Crow Search Algorithm are reduced by replacing the static flight length parameter with our dynamic flight length distribution algorithm. Third, the target selection method (random selection) is replaced by tournament select method. The proposed framework is used to search for architectures on MNIST, CIFAR10, and CIFAR100 datasets and achieved 0.18%, 3.48%, and 15.64% test error, respectively. Furthermore, smallscale transfer experiments are conducted to search architectures for Tiny ImageNet and achieved 34.43% test error. Nonparametric statistical analysis is performed to validate the impact of each modification in improving the quality of search space exploration. The proposed framework has achieved comparable performance with the state-of-the-art approaches, with a comparatively simpler approach and minimum human intervention. The proposed framework can be used to develop completely automated systems for designing architectures for various data-based classification applications.

show abstract

Section: Resultsmentioning

confidence: 91%

Image Classification Based on Automatic Neural Architecture Search Using Binary Crow Search Algorithm

et al. 2020

View full text Add to dashboard Cite

show abstract

“…Various neural networks [22]- [24] have been built to deal with different issues. The BP neural network [25] is a neural network model that combines the network structure of the multilayer perceptron with the error back propagation algorithm, which is mainly divided into three parts: the input layer, the hidden layer and the output layer.…”

Section: Methodology a Bp Neural Networkmentioning

confidence: 99%

The Connectivity Evaluation Among Wells in Reservoir Utilizing Machine Learning Methods

Wang

Wei

et al. 2020

IEEE Access

View full text Add to dashboard Cite

Machine learning is becoming prevalent increasingly for reservoir characteristics analysis in the petroleum industry. This investigation proposes an alternative way for evaluating interwell connectivity in oil fields utilizing machine learning. In this study, three-dimensional convolutional neural network (CNN) was utilized to establish a deep learning model, which can invert interwell connectivity combining with dynamic production data. Different from traditional methods that try to construct mathematical formulas to calculate the connectivity among wells basing on physical laws, deep learning model can capture autonomously the changing characteristics of dynamic production data by training continuously and provide a potential to characterize the interwell connectivity accurately without physical model. At the same time, the back propagation (BP) neural network has also been built to analyze the prediction performance, which are compared with CNN. The results demonstrate that CNN has better performance in predicting the connectivity with the overall AARD below 15.35%. Moreover, the connectivity predicted by CNN is closest to the real connectivity factor compared with some traditional methods. The evaluation method on interwell connectivity proposed by this paper provides effective guidance for the secondary development of both conventional and unconventional reservoirs. INDEX TERMS BP neural network, convolutional neural network, dynamic production data, interwell connectivity, machine learning.

show abstract

“…Image classication has been dominated by variants of convolutional neural networks [12], since it has high learning capacity and steady performance [13], although the recognition accuracy of the convolutional neural network model in image recognition is very high, it is not competitive enough in some fields like recommendation [14]. It requires many labelled image samples for providing training support, current research on image classification mainly relies on manual labelling [15], [16].…”

Section: B Labelling In Image Classificationmentioning

confidence: 99%

Improvement of Ancient Shui Character Recognition Model Based on Convolutional Neural Network

et al. 2020

View full text Add to dashboard Cite

This study uses deep learning theory into the character recognition technology for Shui characters in ancient books, with the objectives of overcoming the instability of the high-pixel ancient Shui characters generative model and the need for large scale handwritten text data annotation among other issues. By constructing a multilayer adversarial neural network with a Laplacian structure, a clear generative model is established for original image data of Shui characters and a stable adversarial network model with multiple mapping relationships from coarse to fine is formed. Based on the analysis of the feature distance of Shui character image samples, the minimum inter-class spacing value and the optimal number of clusters are calculated. Combined with feedback from the classifier model, the optimal number of clusters in the clustering model is adjusted, an evaluation function with information entropy adjustment and clustering threshold convergence is constructed for the unsupervised labelling of Shui character image samples. In this paper, the feedback from the convolutional neural network is used to determine the algorithmic model of the hyperparameters for clustering annotation, and this structure is also designed to improve the recognition rate of handwritten Shui characters in ancient books. INDEX TERMS Shui characters, generative adversarial network, unsupervised labeling.

show abstract

Automatic Convolutional Neural Architecture Search for Image Classification Under Different Scenes

Cited by 43 publications

References 29 publications

Image Classification Based on Automatic Neural Architecture Search Using Binary Crow Search Algorithm

Image Classification Based on Automatic Neural Architecture Search Using Binary Crow Search Algorithm

The Connectivity Evaluation Among Wells in Reservoir Utilizing Machine Learning Methods

Improvement of Ancient Shui Character Recognition Model Based on Convolutional Neural Network

Contact Info

Product

Resources

About